{"id":"https://openalex.org/W2164831377","doi":"https://doi.org/10.48550/arxiv.1301.1936","title":"Risk-Aversion in Multi-armed Bandits","display_name":"Risk-Aversion in Multi-armed Bandits","publication_year":2013,"publication_date":"2013-01-09","ids":{"openalex":"https://openalex.org/W2164831377","doi":"https://doi.org/10.48550/arxiv.1301.1936","mag":"2164831377"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1301.1936","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1301.1936","pdf_url":"https://arxiv.org/pdf/1301.1936","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1301.1936","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006263264","display_name":"Amir Sani","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210138412","display_name":"Centre Inria de l'Universit\u00e9 de Lille","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sani, Amir","raw_affiliation_strings":["INRIA Lille - Nord Europe","Sequential Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Lille - Nord Europe","institution_ids":["https://openalex.org/I4210138412"]},{"raw_affiliation_string":"Sequential Learning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014791481","display_name":"Alessandro Lazaric","orcid":"https://orcid.org/0000-0002-8970-413X","observed_orcids":["https://orcid.org/0000-0002-8970-413X"]},"institutions":[{"id":"https://openalex.org/I4210138412","display_name":"Centre Inria de l'Universit\u00e9 de Lille","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lazaric, Alessandro","raw_affiliation_strings":["INRIA Lille - Nord Europe","Sequential Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Lille - Nord Europe","institution_ids":["https://openalex.org/I4210138412"]},{"raw_affiliation_string":"Sequential Learning","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006533777","display_name":"R\u00e9mi Munos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210138412","display_name":"Centre Inria de l'Universit\u00e9 de Lille","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Munos, R\u00e9mi","raw_affiliation_strings":["INRIA Lille - Nord Europe","Sequential Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Lille - Nord Europe","institution_ids":["https://openalex.org/I4210138412"]},{"raw_affiliation_string":"Sequential Learning","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210138412"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":97,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/risk-aversion","display_name":"risk aversion","score":0.8339999914169312},{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.9559999704360962},{"id":"https://openalex.org/keywords/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.9210000038146973},{"id":"https://openalex.org/keywords/risk-return-trade-off","display_name":"risk-return tradeoff","score":0.9629999995231628},{"id":"https://openalex.org/keywords/exploration-risk","display_name":"exploration risk","score":0.8259999752044678},{"id":"https://openalex.org/keywords/regret","display_name":"regret","score":0.6039999723434448},{"id":"https://openalex.org/keywords/stochastic-multi-armed-bandits","display_name":"stochastic bandits","score":0.6200000047683716},{"id":"https://openalex.org/keywords/bandit-algorithms","display_name":"bandit algorithms","score":0.5690000057220459}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8859966993331909},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.671698808670044},{"id":"https://openalex.org/C129915516","wikidata":"https://www.wikidata.org/wiki/Q17083550","display_name":"Risk aversion (psychology)","level":3,"score":0.6187446713447571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5933432579040527},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5707484483718872},{"id":"https://openalex.org/C2781472820","wikidata":"https://www.wikidata.org/wiki/Q2154759","display_name":"Risk measure","level":3,"score":0.5427227020263672},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.5213364362716675},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.43974828720092773},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.402340292930603},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.35457688570022583},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.25468599796295166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1785125434398651},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16104084253311157},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.08602249622344971},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.06699678301811218},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"pmh:oai:arXiv.org:1301.1936","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1301.1936","pdf_url":"https://arxiv.org/pdf/1301.1936","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.372.7243","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.372.7243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/75/02/98/PDF/risk-bandit.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.764.7544","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.764.7544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1301.1936.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00750298v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00750298","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"[Research Report] 2012","raw_type":"info:eu-repo/semantics/report"},{"id":"pmh:oai:HAL:hal-00772609v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00772609","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"NIPS - Twenty-Sixth Annual Conference on Neural Information Processing Systems, Dec 2012, Lake Tahoe, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1301.1936","doi":"https://doi.org/10.48550/arxiv.1301.1936","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1301.1936","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1301.1936","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1301.1936","pdf_url":"https://arxiv.org/pdf/1301.1936","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1587085269","https://openalex.org/W1590642498","https://openalex.org/W1988645907","https://openalex.org/W1998498767","https://openalex.org/W2016070790","https://openalex.org/W2019291268","https://openalex.org/W2123681024","https://openalex.org/W2124515734","https://openalex.org/W2142971854","https://openalex.org/W2144846366","https://openalex.org/W2159035200","https://openalex.org/W2167875775","https://openalex.org/W2168405694","https://openalex.org/W3027820740"],"related_works":["https://openalex.org/W4285602681","https://openalex.org/W952196006","https://openalex.org/W2142971854","https://openalex.org/W2943626021","https://openalex.org/W2951861381","https://openalex.org/W839588591","https://openalex.org/W7096654391","https://openalex.org/W4408818067","https://openalex.org/W2210427546","https://openalex.org/W7100933069"],"abstract_inverted_index":{"Stochastic":[0],"multi-armed":[1],"bandits":[2],"solve":[3],"the":[4,10,19,24,38,43,49,52,65,83],"Exploration-Exploitation":[5],"dilemma":[6],"and":[7,104],"ultimately":[8],"maximize":[9],"expected":[11,20],"reward.":[12],"Nonetheless,":[13],"in":[14,71],"many":[15],"practical":[16],"problems,":[17],"maximizing":[18],"reward":[21],"is":[22,45],"not":[23],"most":[25],"desirable":[26],"objective.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,95],"introduce":[32,96],"a":[33,79,91],"novel":[34],"setting":[35,57,69],"based":[36],"on":[37],"principle":[39],"of":[40,85,93],"risk-aversion":[41],"where":[42],"objective":[44],"to":[46,59,73,82],"compete":[47],"against":[48],"arm":[50],"with":[51],"best":[53],"risk-return":[54],"trade-off.":[55],"This":[56],"proves":[58],"be":[60],"intrinsically":[61],"more":[62],"difficult":[63],"than":[64],"standard":[66],"multi-arm":[67],"bandit":[68],"due":[70],"part":[72],"an":[74,86],"exploration":[75],"risk":[76],"which":[77],"introduces":[78],"regret":[80],"associated":[81],"variability":[84],"algorithm.":[87],"Using":[88],"variance":[89],"as":[90],"measure":[92],"risk,":[94],"two":[97],"new":[98],"algorithms,":[99],"investigate":[100],"their":[101],"theoretical":[102],"guarantees,":[103],"report":[105],"preliminary":[106],"empirical":[107],"results.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4}],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2016-06-24T00:00:00"}
